56,166 Hits in 6.5 sec

End-to-End Learning for Answering Structured Queries Directly over Text [article]

Paul Groth and Antony Scerri and Ron Daniel, Jr., Bradley P. Allen
2018 arXiv   pre-print
In this work, we present an approach to answer these directly over text data without storing results in a database.  ...  Triple Pattern Fragments) with models built for extractive question answering. Importantly, by applying distributed querying answering we are able to simplify the model learning problem.  ...  Wikidata has a number of properties that make it useful for building a corpus to learn how to answer structured queries over text.  ... 
arXiv:1811.06303v2 fatcat:zi3v3rgowbcm5fouetacmucilq

Recent Advances in Automated Question Answering In Biomedical Domain [article]

Krishanu Das Baksi
2021 arXiv   pre-print
The objective of automated Question Answering (QA) systems is to provide answers to user queries in a time efficient manner.  ...  datasets and several proposed approaches, both using structured databases and collection of texts.  ...  Although it is easier than learning to write structured queries in SQL, users need to be familiar with the semi structured query language method to use the system.  ... 
arXiv:2111.05937v1 fatcat:5474jk6ozbalvmfjrgatu4tsna

QnAMaker: Data to Bot in 2 Minutes [article]

Parag Agrawal, Tulasi Menon, Aya Kamel, Michel Naim, Chaikesh Chouragade, Gurvinder Singh, Rohan Kulkarni, Anshuman Suri, Sahithi Katakam, Vineet Pratik, Prakul Bansal, Simerpreet Kaur, Neha Rajput (+4 others)
2020 arXiv   pre-print
These bots help reduce traffic received by human support significantly by handling frequent and directly answerable known questions.  ...  A conversation layer over such raw data can lower traffic to human support by a great margin.  ...  add a conversational layer over semi-structured user data.  ... 
arXiv:2003.08553v1 fatcat:b7ht6uj3pvaulfmrnqwqdqrnba

Systematic review of question answering over knowledge bases

Arnaldo Pereira, Alina Trifan, Rui Pedro Lopes, José Luís Oliveira
2021 IET Software  
The inclusion criteria rationale was English full-text articles published since 2015 on methods and systems for KBQAs.  ...  Because question answering over knowledge bases (KBQAs) is a very active research topic, a comprehensive view of the field is essential.  ...  pipe. 2016 26 When a knowledge base is not enough: Question answering over knowledge bases with external text data [39] Info. extraction 2016 27 An end-to-end model for question answering over  ... 
doi:10.1049/sfw2.12028 fatcat:uuhsewdvsnal5hwua3lecfexqi

Differentiable Reasoning over a Virtual Knowledge Base [article]

Bhuwan Dhingra, Manzil Zaheer, Vidhisha Balachandran, Graham Neubig, Ruslan Salakhutdinov, William W. Cohen
2020 arXiv   pre-print
On HotpotQA, DrKIT leads to a 10% improvement over a BERT-based re-ranking approach to retrieving the relevant passages required to answer a question.  ...  This module is differentiable, so the full system can be trained end-to-end using gradient based methods, starting from natural language inputs.  ...  We introduce an efficient, end-to-end differentiable framework for doing complex QA over a large text corpus that has been encoded in a query-independent manner.  ... 
arXiv:2002.10640v1 fatcat:2fcnpovwjjfdvfl36nvhoj3u54

Span-based Localizing Network for Natural Language Video Localization [article]

Hao Zhang, Aixin Sun, Wei Jing, Joey Tianyi Zhou
2020 arXiv   pre-print
Given an untrimmed video and a text query, natural language video localization (NLVL) is to locate a matching span from the video that semantically corresponds to the query.  ...  The QGH guides VSLNet to search for matching video span within a highlighted region.  ...  Acknowledgments This research is supported by the Agency for Science, Technology and Research (A*STAR) under its AME Programmatic Funding Scheme (Project #A18A1b0045 and #A18A2b0046).  ... 
arXiv:2004.13931v2 fatcat:ifau7knpgrdgfgpc7xl7nty63m

Document Representation [chapter]

Zhiyuan Liu, Yankai Lin, Maosong Sun
2020 Representation Learning for Natural Language Processing  
The task is to extract a most likely text span from the passage as the answer to the question, which is usually modeled as predicting the start position idx start and end position idx end of the answer  ...  so as to more directly impact the generation of words across longer spans of text.  ... 
doi:10.1007/978-981-15-5573-2_5 fatcat:e2olk7crlrhsxgcrobtu3e3ifa

Neural Speed Reading with Structural-Jump-LSTM [article]

Christian Hansen, Casper Hansen, Stephen Alstrup, Jakob Grue Simonsen, Christina Lioma
2019 arXiv   pre-print
, or end of text markers) to jump ahead after reading a word.  ...  We present Structural-Jump-LSTM: the first neural speed reading model to both skip and jump text during inference.  ...  , or to the end of the text (which is also an instance of end of sentence).  ... 
arXiv:1904.00761v2 fatcat:imch75zsobfjlkcp7xania6m2e

Does Structure Matter? Leveraging Data-to-Text Generation for Answering Complex Information Needs [article]

Hanane Djeddal, Thomas Gerald, Laure Soulier, Karen Pinel-Sauvagnat, Lynda Tamine
2021 arXiv   pre-print
We evaluate both the generated answer and its corresponding structure and show the effectiveness of planning-based models in comparison to a text-to-text model.  ...  In this work, our aim is to provide a structured answer in natural language to a complex information need.  ...  Acknowledgement We would like to thank projects ANR JCJC SESAMS (ANR-18-CE23-0001) and ANR COST (ANR-18-CE23-0016) for supporting this work.  ... 
arXiv:2112.04344v1 fatcat:cxscuzygtrd7hkssb4hdibo7wm

ISCAS at SemEval-2020 Task 5: Pre-trained Transformers for Counterfactual Statement Modeling [article]

Yaojie Lu and Annan Li and Hongyu Lin and Xianpei Han and Le Sun
2020 arXiv   pre-print
For the second subtask, we formulate antecedent and consequence extraction as a query-based question answering problem. The two subsystems both achieved third place in the evaluation.  ...  For the first subtask, we train several transformer-based classifiers for detecting counterfactual statements.  ...  Answer Prediction. To extract continuous text fragments, we employ a pointer network to predict the start position and end position of the answer text.  ... 
arXiv:2009.08171v1 fatcat:guts2ddkmrbsvhn4y6rkpzffq4

CWM global search - an internet search engine for the chemist

Alexander Kos, H-J Himmler
2010 Journal of Cheminformatics  
It should be obvious that an end user is a) not aware of all the resources, and b) has not the time to learn every user interface and is unable to search over all of them.  ...  We provide CWM Global Search as an application that enables to search by structure, CAS Registry Number and free text over all these sources.  ... 
doi:10.1186/1758-2946-2-s1-p1 pmcid:PMC2867141 fatcat:eifi36jybjhbzfzdi2p5lgzctm

R2D2: A Dbpedia Chatbot Using Triple-Pattern Like Queries

Haridimos Kondylakis, Dimitrios Tsirigotakis, Giorgos Fragkiadakis, Emmanouela Panteri, Alexandros Papadakis, Alexandros Fragkakis, Eleytherios Tzagkarakis, Ioannis Rallis, Zacharias Saridakis, Apostolos Trampas, Giorgos Pirounakis, Nikolaos Papadakis
2020 Algorithms  
The chatbot accepts structured input, allowing users to enter triple-pattern like queries, which are answered by the underlying engine.  ...  The queries are submitted to the corresponding DBpedia SPARQL endpoint, and then the result is received by R2D2 and augmented with maps and visuals and eventually presented to the user.  ...  the answer to the end-user using nice cards, graphs, and maps.  ... 
doi:10.3390/a13090217 fatcat:tvllkaq74fdltjazt3vmgxi6py

Linguistic and semantic passage retrieval strategies for question answering

Matthew W. Bilotti
2011 SIGIR Forum  
Linguistic and semantic passage retrieval methods are also shown to improve end-to-end QA system accuracy and answer MRR. iv Acknowledgments I would like to thank my advisor, Eric Nyberg, for all he has  ...  Question Answering (QA) is the task of searching a large text collection for specific answers to questions posed in natural language.  ...  The better quality passage ranking provided by the learning-to-rank method was shown to be able to translate into improved end-to-end QA system performance in terms of answer accuracy for certain types  ... 
doi:10.1145/1924475.1924495 fatcat:cbzirz6ua5bpnndsn4zs7zx5uy

Neural Architecture for Question Answering Using a Knowledge Graph and Web Corpus [article]

Uma Sawant, Saurabh Garg, Soumen Chakrabarti, Ganesh Ramakrishnan
2018 arXiv   pre-print
It may use a parser to interpret the question to a structured query, execute that on a knowledge graph (KG), and return direct entity responses.  ...  On four public query workloads, amounting to over 8,000 queries with diverse query syntax, we see 5--16% absolute improvement in mean average precision (MAP), compared to the entity ranking performance  ...  Acknowledgment: Thanks to the reviewers for their constructive suggestions. Thanks to Elmar Haußmann for generous help with AQQU. Thanks to Doug Oard for advice on set vs. ranked retrieval.  ... 
arXiv:1706.00973v3 fatcat:le523ev5u5bg3amdieimu43hgm

A Hybrid Embedding Approach to Noisy Answer Passage Retrieval [chapter]

Daniel Cohen, W. Bruce Croft
2018 Lecture Notes in Computer Science  
Recent work with deep learning has shown the efficacy of distributed text representations for retrieving sentences or tokens for question answering.  ...  However, determining the relevancy of answer passages remains a significant challenge, specifically when there exists a lexical and semantic gap between the text representation used for training and the  ...  Acknowledgments This work was supported in part by the Center for Intelligent Information Retrieval, in part by NSF IIS-1160894 and in part by NSF grant #IIS-1419693.  ... 
doi:10.1007/978-3-319-76941-7_10 fatcat:6glb3eh65rg3ng5rfatuz5edim
« Previous Showing results 1 — 15 out of 56,166 results